No Cover Image

Conference Paper/Proceeding/Abstract 1098 views

A Multi-Stage Random Forest Classifier for Phase Contrast Cell Segmentation

Ehab Essa, Rachel Errington, Nick White, Xianghua Xie Orcid Logo

37th Annual Int. Conf. IEEE Engineering in Medicine and Biology Society

Swansea University Author: Xianghua Xie Orcid Logo

Abstract

We present a machine learning based approach to automatically detect and segment cells in phase contrast images. The proposed method consists of a multi-stage classification scheme based on random forest (RF) classifier. Both low level and mid level image features are used to determine meaningful ce...

Full description

Published in: 37th Annual Int. Conf. IEEE Engineering in Medicine and Biology Society
Published: 2015
URI: https://cronfa.swan.ac.uk/Record/cronfa22235
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2015-07-02T02:07:56Z
last_indexed 2018-02-09T05:00:30Z
id cronfa22235
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2015-07-01T10:22:48.4719159</datestamp><bib-version>v2</bib-version><id>22235</id><entry>2015-07-01</entry><title>A Multi-Stage Random Forest Classifier for Phase Contrast Cell Segmentation</title><swanseaauthors><author><sid>b334d40963c7a2f435f06d2c26c74e11</sid><ORCID>0000-0002-2701-8660</ORCID><firstname>Xianghua</firstname><surname>Xie</surname><name>Xianghua Xie</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2015-07-01</date><deptcode>SCS</deptcode><abstract>We present a machine learning based approach to automatically detect and segment cells in phase contrast images. The proposed method consists of a multi-stage classification scheme based on random forest (RF) classifier. Both low level and mid level image features are used to determine meaningful cell regions. Pixel-wise RF classification is first carried out to categorize pixels into 4 classes (dark cell, bright cell, halo artifact, and background) and generate a probability map for cell regions. K-means clustering is then applied on the probability map to group similar pixels into candidate cell regions. Finally, cell validation is performed by another RF to verify the candidate cell regions. The proposed method has been tested on U2-OS human osteosarcoma phase contrast images. The experimental results show better performance of the proposed method with precision 92.96% and recall 96.63% compared to a state-of-the-art segmentation technique.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>37th Annual Int. Conf. IEEE Engineering in Medicine and Biology Society</journal><publisher/><keywords>Cell segmentation, medical image analysis, random forests</keywords><publishedDay>31</publishedDay><publishedMonth>8</publishedMonth><publishedYear>2015</publishedYear><publishedDate>2015-08-31</publishedDate><doi/><url/><notes/><college>COLLEGE NANME</college><department>Computer Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2015-07-01T10:22:48.4719159</lastEdited><Created>2015-07-01T10:20:58.1473015</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Ehab</firstname><surname>Essa</surname><order>1</order></author><author><firstname>Rachel</firstname><surname>Errington</surname><order>2</order></author><author><firstname>Nick</firstname><surname>White</surname><order>3</order></author><author><firstname>Xianghua</firstname><surname>Xie</surname><orcid>0000-0002-2701-8660</orcid><order>4</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling 2015-07-01T10:22:48.4719159 v2 22235 2015-07-01 A Multi-Stage Random Forest Classifier for Phase Contrast Cell Segmentation b334d40963c7a2f435f06d2c26c74e11 0000-0002-2701-8660 Xianghua Xie Xianghua Xie true false 2015-07-01 SCS We present a machine learning based approach to automatically detect and segment cells in phase contrast images. The proposed method consists of a multi-stage classification scheme based on random forest (RF) classifier. Both low level and mid level image features are used to determine meaningful cell regions. Pixel-wise RF classification is first carried out to categorize pixels into 4 classes (dark cell, bright cell, halo artifact, and background) and generate a probability map for cell regions. K-means clustering is then applied on the probability map to group similar pixels into candidate cell regions. Finally, cell validation is performed by another RF to verify the candidate cell regions. The proposed method has been tested on U2-OS human osteosarcoma phase contrast images. The experimental results show better performance of the proposed method with precision 92.96% and recall 96.63% compared to a state-of-the-art segmentation technique. Conference Paper/Proceeding/Abstract 37th Annual Int. Conf. IEEE Engineering in Medicine and Biology Society Cell segmentation, medical image analysis, random forests 31 8 2015 2015-08-31 COLLEGE NANME Computer Science COLLEGE CODE SCS Swansea University 2015-07-01T10:22:48.4719159 2015-07-01T10:20:58.1473015 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Ehab Essa 1 Rachel Errington 2 Nick White 3 Xianghua Xie 0000-0002-2701-8660 4
title A Multi-Stage Random Forest Classifier for Phase Contrast Cell Segmentation
spellingShingle A Multi-Stage Random Forest Classifier for Phase Contrast Cell Segmentation
Xianghua Xie
title_short A Multi-Stage Random Forest Classifier for Phase Contrast Cell Segmentation
title_full A Multi-Stage Random Forest Classifier for Phase Contrast Cell Segmentation
title_fullStr A Multi-Stage Random Forest Classifier for Phase Contrast Cell Segmentation
title_full_unstemmed A Multi-Stage Random Forest Classifier for Phase Contrast Cell Segmentation
title_sort A Multi-Stage Random Forest Classifier for Phase Contrast Cell Segmentation
author_id_str_mv b334d40963c7a2f435f06d2c26c74e11
author_id_fullname_str_mv b334d40963c7a2f435f06d2c26c74e11_***_Xianghua Xie
author Xianghua Xie
author2 Ehab Essa
Rachel Errington
Nick White
Xianghua Xie
format Conference Paper/Proceeding/Abstract
container_title 37th Annual Int. Conf. IEEE Engineering in Medicine and Biology Society
publishDate 2015
institution Swansea University
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str 0
active_str 0
description We present a machine learning based approach to automatically detect and segment cells in phase contrast images. The proposed method consists of a multi-stage classification scheme based on random forest (RF) classifier. Both low level and mid level image features are used to determine meaningful cell regions. Pixel-wise RF classification is first carried out to categorize pixels into 4 classes (dark cell, bright cell, halo artifact, and background) and generate a probability map for cell regions. K-means clustering is then applied on the probability map to group similar pixels into candidate cell regions. Finally, cell validation is performed by another RF to verify the candidate cell regions. The proposed method has been tested on U2-OS human osteosarcoma phase contrast images. The experimental results show better performance of the proposed method with precision 92.96% and recall 96.63% compared to a state-of-the-art segmentation technique.
published_date 2015-08-31T03:26:28Z
_version_ 1763750957640843264
score 11.036706

Similar Items